HyperAI

Arithmetic Reasoning On Game Of 24

Metriken

Success

Ergebnisse

Leistungsergebnisse verschiedener Modelle zu diesem Benchmark

Modellname
Success
Paper TitleRepository
Tree of Thoughts (b=5)0.74Tree of Thoughts: Deliberate Problem Solving with Large Language Models
0 of 1 row(s) selected.